Discrete reproducing kernel Hilbert spaces: sampling and distribution of Dirac-masses

MaRDI QIDQ2788397zbMATH OpenFDO

Authors Palle Jorgensen, Feng Tian

Publication date 19 February 2016

Published in Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1501.02310, http://jmlr.csail.mit.edu/papers/v16/jorgensen15a.html

zbMATH Keywords

reproducing kernel Hilbert spacesgraph Laplaciansresistance metricdiscrete green's functionssampling in discrete systems

Mathematics Subject Classification ID

Gaussian processes (60G15) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22)

Abstract: We study reproducing kernels, and associated reproducing kernel Hilbert spaces (RKHSs) $mathscrH$ over infinite, discrete and countable sets $V$. In this setting we analyze in detail the distributions of the corresponding Dirac point-masses of $V$. Illustrations include certain models from neural networks: An Extreme Learning Machine (ELM) is a neural network-configuration in which a hidden layer of weights are randomly sampled, and where the object is then to compute resulting output. For RKHSs $mathscrH$ of functions defined on a prescribed countable infinite discrete set $V$, we characterize those which contain the Dirac masses $delt{a}_x$ for all points $x$ in $V$. Further examples and applications where this question plays an important role are: (i) discrete Brownian motion-Hilbert spaces, i.e., discrete versions of the Cameron-Martin Hilbert space; (ii) energy-Hilbert spaces corresponding to graph-Laplacians where the set $V$ of vertices is then equipped with a resistance metric; and finally (iii) the study of Gaussian free fields.

Recommendations

• Graph Laplacians and discrete reproducing kernel Hilbert spaces from restrictions
• Nonuniform sampling, reproducing kernels, and the associated Hilbert spaces
• On the stability of reproducing kernel Hilbert spaces of discrete-time impulse responses
• Continuum versus discrete networks, graph Laplacians, and reproducing kernel Hilbert spaces
• Reproducing kernel Hilbert spaces on manifolds: Sobolev and diffusion spaces

Cited in

(17)

• New Hilbert space tools for analysis of graph Laplacians and Markov processes
• scientific article; zbMATH DE number 7626740 (Why is no real title available?)
• Three types of reproducing kernel Hilbert spaces of polynomials
• Decomposition of Gaussian processes, and factorization of positive definite kernels
• Realizations and factorizations of positive definite kernels
• Dual spaces of restrictions in the reproducing kernel Hilbert spaces in discrete sets
• Nonuniform sampling, reproducing kernels, and the associated Hilbert spaces
• Metric duality between positive definite kernels and boundary processes
• Harmonic analysis of network systems via kernels and their boundary realizations
• Continuum versus discrete networks, graph Laplacians, and reproducing kernel Hilbert spaces
• Gram matrices of reproducing kernel Hilbert spaces over graphs. IV: Quadratic inequalities for graph Laplacians
• Noncommutative boundaries arising in dynamics and representations of the Cuntz relations
• Reproducing kernels: harmonic analysis and some of their applications
• Kernel partial correlation: a novel approach to capturing conditional independence in graphical models for noisy data
• System identification in dynamical sampling
• Graph Laplacians and discrete reproducing kernel Hilbert spaces from restrictions
• Harmonic analysis on graphs via Bratteli diagrams and path-space measures

This page was built for publication: Discrete reproducing kernel Hilbert spaces: sampling and distribution of Dirac-masses

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2788397)